3 papers
cs.CL2026
StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions
Chao Gao, Haijiang Liu, Qiyuan Li +3
Large language models often answer the same multiple-choice question inconsistently when it is posed under support-oriented and elimination-oriented framings. We investigate whethe…
cs.CL2025
Beyond Demographics: Enhancing Cultural Value Survey Simulation with Multi-Stage Personality-Driven Cognitive Reasoning
Haijiang Liu, Qiyuan Li, Chao Gao +5
Introducing MARK, the Multi-stAge Reasoning frameworK for cultural value survey response simulation, designed to enhance the accuracy, steerability, and interpretability of large l…
cs.AI2025
Reviewing Clinical Knowledge in Medical Large Language Models: Training and Beyond
Qiyuan Li, Haijiang Liu, Caicai Guo +6
The large-scale development of large language models (LLMs) in medical contexts, such as diagnostic assistance and treatment recommendations, necessitates that these models possess…